Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents,...
cat ~/New
Browse newest skills added to the marketplace
15,688 skills
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps,...
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile...
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments...
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production...
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production...
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs,...
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment,...
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend...
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking...
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when...
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision...
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on...
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer...
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when...
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is...
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when...
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or...
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without...
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances...
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of...
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks...
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision,...
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies....